Skip to content

[CUDA] Run FlashAttention regression test only when FlashAttention is available #27206

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hariharans29 merged 3 commits into from
Feb 4, 2026
Merged

[CUDA] Run FlashAttention regression test only when FlashAttention is available #27206

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4e9cc07
Run FLashAttention regression test only when FlashAttention is available
hariharans29 Jan 29, 2026
970418d
Update onnxruntime/test/python/transformers/test_gqa.py
hariharans29 Jan 29, 2026
65c0706
Merge remote-tracking branch 'origin' into hari/fix_GQA_build_errors
hariharans29 Jan 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion onnxruntime/test/python/transformers/test_gqa.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1774,7 +1774,7 @@ def test_flash_decode_parity(self):
# Clean up
del os.environ["ORT_DISABLE_FLASH_DECODE"]

Comment thread
hariharans29 marked this conversation as resolved.

@unittest.skipIf(not has_flash_attention(), "Flash Attention is not available, skipping tests.")
class TestGQARegressions(unittest.TestCase):
"""Specific regression tests for historical bugs."""

Expand Down
Loading